Retail · Customer experience
AI voice agent proof of concept for a European fashion retailer
An AI voice agent proof of concept for a European clothing and lifestyle retailer, handling calls from customers about orders they have already placed.
Proof of concept
The problem and the starting point
Customers calling about orders they had placed were waiting, and too many calls went unanswered. Finding an order and where it had got to took staff too long, and calls were not always reaching the right person.
What is being trialled
- An AI voice agent for part of the after-order customer journey. It finds the customer's order in the courier network and tells them when it will be delivered.
People and safeguards
- Everything else is triaged, so calls that need a person go straight to the right team.
Results so far
The proof of concept is in progress. No results are claimed yet.
What the figures show
Results will be measured against the baseline and published here once available.
How an order and delivery voice agent works
General background from our guide to AI voice agents, not findings from this proof of concept. No results from this trial are claimed here.
What an agent like this can do
- Answer every call, including at busy times, lunchtimes and out of hours.
- Understand questions in the caller's own words, rather than asking them to press a number.
- Look the order up in the systems it is connected to and give a specific delivery update. In this proof of concept, that is the courier network.
- Send a text message with a link or confirmation after the call.
Where a person is still needed
- Complaints where the caller is upset and wants to be heard by a person.
- Complicated problems that cross several departments or need a decision.
- Vulnerable callers, or calls where someone's health, safety or finances are at risk.
- Anything the agent has not been given accurate information or system access to answer.
Good practice for handing over
- Callers are told at the start that they are speaking to AI.
- Callers can ask for a person at any point. Where nobody is available, the agent can take a message, book a callback or send a text.
- When a call is transferred, the colleague sees who is calling, what they asked and what the AI has already done.
Measures a trial like this usually tracks
- Answer rate: the share of calls answered rather than missed or abandoned.
- Resolution rate: calls fully dealt with by the AI without a person.
- Transfer rate and reasons: which calls go to a person, and why.
- Repeat calls: whether callers ring back about the same order.
- Customer feedback: a short survey or a sample of reviewed calls.
Further reading
Choose your next step
Explore on your own
About ten minutes. See where AI could release time in your business.
Discuss a specific problem
A free 30-minute video call with Keith about your situation.
Quick question
Ask about our services or the right next step, at any time.